Triple

T17456797
Position Surface form Disambiguated ID Type / Status
Subject Sežana E425050 entity
Predicate nearbySettlement P350 FINISHED
Object Divača
Divača is a small town in southwestern Slovenia known as a transport hub and gateway to the nearby Škocjan Caves, a UNESCO World Heritage site.
E1269872 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Divača | Statement: [Sežana, nearbySettlement, Divača]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Divača
Context triple: [Sežana, nearbySettlement, Divača]
  • A. Sjenica
    Sjenica is a town in southwestern Serbia known for its harsh winters, high-altitude plateau setting, and production of the famous Sjenica cheese.
  • B. Bezdružice
    Bezdružice is a small town in the Plzeň Region of the Czech Republic known for its historic chateau and rural character.
  • C. Draga Mašin
    Draga Mašin was the controversial Queen of Serbia whose marriage to King Alexander I and unpopularity at court contributed to the 1903 May Coup in which both were assassinated.
  • D. Povljana
    Povljana is a coastal municipality and tourist settlement on the island of Pag in Croatia, known for its beaches and Mediterranean landscape.
  • E. Damski Czepek
    Damski Czepek is a sculptural artwork by Ursula von Rydingsvard, reflecting her characteristic use of organic forms and textured surfaces.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Divača
Triple: [Sežana, nearbySettlement, Divača]
Generated description
Divača is a small town in southwestern Slovenia known as a transport hub and gateway to the nearby Škocjan Caves, a UNESCO World Heritage site.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Divača
Target entity description: Divača is a small town in southwestern Slovenia known as a transport hub and gateway to the nearby Škocjan Caves, a UNESCO World Heritage site.
  • A. Sjenica
    Sjenica is a town in southwestern Serbia known for its harsh winters, high-altitude plateau setting, and production of the famous Sjenica cheese.
  • B. Bezdružice
    Bezdružice is a small town in the Plzeň Region of the Czech Republic known for its historic chateau and rural character.
  • C. Draga Mašin
    Draga Mašin was the controversial Queen of Serbia whose marriage to King Alexander I and unpopularity at court contributed to the 1903 May Coup in which both were assassinated.
  • D. Povljana
    Povljana is a coastal municipality and tourist settlement on the island of Pag in Croatia, known for its beaches and Mediterranean landscape.
  • E. Damski Czepek
    Damski Czepek is a sculptural artwork by Ursula von Rydingsvard, reflecting her characteristic use of organic forms and textured surfaces.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e45142b08481908cdd290692d796c3 completed April 19, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01b0007a748190832a795448a1cfc4 completed May 11, 2026, 10:31 a.m.
NEDg Description generation batch_6a01b0cd1df481908c760bdfcacba496 completed May 11, 2026, 10:34 a.m.
NED2 Entity disambiguation (via description) batch_6a01b208e6d8819080a363da368ec2e9 completed May 11, 2026, 10:40 a.m.
Created at: April 10, 2026, 5:47 a.m.